X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=mm%2Fslub.c;h=a90c4ffc95765e3c16965473d3b51b262ea91f0b;hb=e12ba74d8ff3e2f73a583500d7095e406df4d093;hp=6c6d74ff06941e0baf4d923cc0f103e2b1e7297d;hpb=2208b764c14d0f1ad63da64b1a42db6077b6fe42;p=linux-2.6

diff --git a/mm/slub.c b/mm/slub.c
index 6c6d74ff06..a90c4ffc95 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -211,7 +211,8 @@ static inline void ClearSlabDebug(struct page *page)
 #define MAX_OBJECTS_PER_SLAB 65535
 
 /* Internal SLUB flags */
-#define __OBJECT_POISON 0x80000000	/* Poison object */
+#define __OBJECT_POISON		0x80000000 /* Poison object */
+#define __SYSFS_ADD_DEFERRED	0x40000000 /* Not yet visible via sysfs */
 
 /* Not all arches define cache_line_size */
 #ifndef cache_line_size
@@ -985,7 +986,9 @@ out:
 
 __setup("slub_debug", setup_slub_debug);
 
-static void kmem_cache_open_debug_check(struct kmem_cache *s)
+static unsigned long kmem_cache_flags(unsigned long objsize,
+	unsigned long flags, const char *name,
+	void (*ctor)(void *, struct kmem_cache *, unsigned long))
 {
 	/*
 	 * The page->offset field is only 16 bit wide. This is an offset
@@ -999,19 +1002,21 @@ static void kmem_cache_open_debug_check(struct kmem_cache *s)
 	 * Debugging or ctor may create a need to move the free
 	 * pointer. Fail if this happens.
 	 */
-	if (s->objsize >= 65535 * sizeof(void *)) {
-		BUG_ON(s->flags & (SLAB_RED_ZONE | SLAB_POISON |
+	if (objsize >= 65535 * sizeof(void *)) {
+		BUG_ON(flags & (SLAB_RED_ZONE | SLAB_POISON |
 				SLAB_STORE_USER | SLAB_DESTROY_BY_RCU));
-		BUG_ON(s->ctor);
-	}
-	else
+		BUG_ON(ctor);
+	} else {
 		/*
 		 * Enable debugging if selected on the kernel commandline.
 		 */
 		if (slub_debug && (!slub_debug_slabs ||
-		    strncmp(slub_debug_slabs, s->name,
+		    strncmp(slub_debug_slabs, name,
 		    	strlen(slub_debug_slabs)) == 0))
-				s->flags |= slub_debug;
+				flags |= slub_debug;
+	}
+
+	return flags;
 }
 #else
 static inline void setup_object_debug(struct kmem_cache *s,
@@ -1028,7 +1033,12 @@ static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
 static inline int check_object(struct kmem_cache *s, struct page *page,
 			void *object, int active) { return 1; }
 static inline void add_full(struct kmem_cache_node *n, struct page *page) {}
-static inline void kmem_cache_open_debug_check(struct kmem_cache *s) {}
+static inline unsigned long kmem_cache_flags(unsigned long objsize,
+	unsigned long flags, const char *name,
+	void (*ctor)(void *, struct kmem_cache *, unsigned long))
+{
+	return flags;
+}
 #define slub_debug 0
 #endif
 /*
@@ -1045,6 +1055,9 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	if (s->flags & SLAB_CACHE_DMA)
 		flags |= SLUB_DMA;
 
+	if (s->flags & SLAB_RECLAIM_ACCOUNT)
+		flags |= __GFP_RECLAIMABLE;
+
 	if (node == -1)
 		page = alloc_pages(flags, s->order);
 	else
@@ -1078,12 +1091,13 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	void *last;
 	void *p;
 
-	BUG_ON(flags & ~(GFP_DMA | __GFP_ZERO | GFP_LEVEL_MASK));
+	BUG_ON(flags & GFP_SLAB_BUG_MASK);
 
 	if (flags & __GFP_WAIT)
 		local_irq_enable();
 
-	page = allocate_slab(s, flags & GFP_LEVEL_MASK, node);
+	page = allocate_slab(s,
+		flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
 	if (!page)
 		goto out;
 
@@ -1868,17 +1882,24 @@ static void init_kmem_cache_node(struct kmem_cache_node *n)
  * Note that this function only works on the kmalloc_node_cache
  * when allocating for the kmalloc_node_cache.
  */
-static struct kmem_cache_node * __init early_kmem_cache_node_alloc(gfp_t gfpflags,
-								int node)
+static struct kmem_cache_node *early_kmem_cache_node_alloc(gfp_t gfpflags,
+							   int node)
 {
 	struct page *page;
 	struct kmem_cache_node *n;
 
 	BUG_ON(kmalloc_caches->size < sizeof(struct kmem_cache_node));
 
-	page = new_slab(kmalloc_caches, gfpflags | GFP_THISNODE, node);
+	page = new_slab(kmalloc_caches, gfpflags, node);
 
 	BUG_ON(!page);
+	if (page_to_nid(page) != node) {
+		printk(KERN_ERR "SLUB: Unable to allocate memory from "
+				"node %d\n", node);
+		printk(KERN_ERR "SLUB: Allocating a useless per node structure "
+				"in order to be able to continue\n");
+	}
+
 	n = page->freelist;
 	BUG_ON(!n);
 	page->freelist = get_freepointer(kmalloc_caches, n);
@@ -1904,7 +1925,7 @@ static void free_kmem_cache_nodes(struct kmem_cache *s)
 {
 	int node;
 
-	for_each_online_node(node) {
+	for_each_node_state(node, N_NORMAL_MEMORY) {
 		struct kmem_cache_node *n = s->node[node];
 		if (n && n != &s->local_node)
 			kmem_cache_free(kmalloc_caches, n);
@@ -1922,7 +1943,7 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
 	else
 		local_node = 0;
 
-	for_each_online_node(node) {
+	for_each_node_state(node, N_NORMAL_MEMORY) {
 		struct kmem_cache_node *n;
 
 		if (local_node == node)
@@ -2080,9 +2101,8 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
 	s->name = name;
 	s->ctor = ctor;
 	s->objsize = size;
-	s->flags = flags;
 	s->align = align;
-	kmem_cache_open_debug_check(s);
+	s->flags = kmem_cache_flags(size, flags, name, ctor);
 
 	if (!calculate_sizes(s))
 		goto error;
@@ -2176,7 +2196,7 @@ static inline int kmem_cache_close(struct kmem_cache *s)
 	flush_all(s);
 
 	/* Attempt to free all objects */
-	for_each_online_node(node) {
+	for_each_node_state(node, N_NORMAL_MEMORY) {
 		struct kmem_cache_node *n = get_node(s, node);
 
 		n->nr_partial -= free_list(s, n, &n->partial);
@@ -2211,11 +2231,11 @@ EXPORT_SYMBOL(kmem_cache_destroy);
  *		Kmalloc subsystem
  *******************************************************************/
 
-struct kmem_cache kmalloc_caches[KMALLOC_SHIFT_HIGH + 1] __cacheline_aligned;
+struct kmem_cache kmalloc_caches[PAGE_SHIFT] __cacheline_aligned;
 EXPORT_SYMBOL(kmalloc_caches);
 
 #ifdef CONFIG_ZONE_DMA
-static struct kmem_cache *kmalloc_caches_dma[KMALLOC_SHIFT_HIGH + 1];
+static struct kmem_cache *kmalloc_caches_dma[PAGE_SHIFT];
 #endif
 
 static int __init setup_slub_min_order(char *str)
@@ -2277,10 +2297,26 @@ panic:
 }
 
 #ifdef CONFIG_ZONE_DMA
+
+static void sysfs_add_func(struct work_struct *w)
+{
+	struct kmem_cache *s;
+
+	down_write(&slub_lock);
+	list_for_each_entry(s, &slab_caches, list) {
+		if (s->flags & __SYSFS_ADD_DEFERRED) {
+			s->flags &= ~__SYSFS_ADD_DEFERRED;
+			sysfs_slab_add(s);
+		}
+	}
+	up_write(&slub_lock);
+}
+
+static DECLARE_WORK(sysfs_add_work, sysfs_add_func);
+
 static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
 {
 	struct kmem_cache *s;
-	struct kmem_cache *x;
 	char *text;
 	size_t realsize;
 
@@ -2289,22 +2325,36 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
 		return s;
 
 	/* Dynamically create dma cache */
-	x = kmalloc(kmem_size, flags & ~SLUB_DMA);
-	if (!x)
-		panic("Unable to allocate memory for dma cache\n");
+	if (flags & __GFP_WAIT)
+		down_write(&slub_lock);
+	else {
+		if (!down_write_trylock(&slub_lock))
+			goto out;
+	}
+
+	if (kmalloc_caches_dma[index])
+		goto unlock_out;
 
 	realsize = kmalloc_caches[index].objsize;
-	text = kasprintf(flags & ~SLUB_DMA, "kmalloc_dma-%d",
-			(unsigned int)realsize);
-	s = create_kmalloc_cache(x, text, realsize, flags);
-	down_write(&slub_lock);
-	if (!kmalloc_caches_dma[index]) {
-		kmalloc_caches_dma[index] = s;
-		up_write(&slub_lock);
-		return s;
+	text = kasprintf(flags & ~SLUB_DMA, "kmalloc_dma-%d", (unsigned int)realsize),
+	s = kmalloc(kmem_size, flags & ~SLUB_DMA);
+
+	if (!s || !text || !kmem_cache_open(s, flags, text,
+			realsize, ARCH_KMALLOC_MINALIGN,
+			SLAB_CACHE_DMA|__SYSFS_ADD_DEFERRED, NULL)) {
+		kfree(s);
+		kfree(text);
+		goto unlock_out;
 	}
+
+	list_add(&s->list, &slab_caches);
+	kmalloc_caches_dma[index] = s;
+
+	schedule_work(&sysfs_add_work);
+
+unlock_out:
 	up_write(&slub_lock);
-	kmem_cache_destroy(s);
+out:
 	return kmalloc_caches_dma[index];
 }
 #endif
@@ -2351,12 +2401,8 @@ static struct kmem_cache *get_slab(size_t size, gfp_t flags)
 			return ZERO_SIZE_PTR;
 
 		index = size_index[(size - 1) / 8];
-	} else {
-		if (size > KMALLOC_MAX_SIZE)
-			return NULL;
-
+	} else
 		index = fls(size - 1);
-	}
 
 #ifdef CONFIG_ZONE_DMA
 	if (unlikely((flags & SLUB_DMA)))
@@ -2368,9 +2414,15 @@ static struct kmem_cache *get_slab(size_t size, gfp_t flags)
 
 void *__kmalloc(size_t size, gfp_t flags)
 {
-	struct kmem_cache *s = get_slab(size, flags);
+	struct kmem_cache *s;
 
-	if (ZERO_OR_NULL_PTR(s))
+	if (unlikely(size > PAGE_SIZE / 2))
+		return (void *)__get_free_pages(flags | __GFP_COMP,
+							get_order(size));
+
+	s = get_slab(size, flags);
+
+	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
 	return slab_alloc(s, flags, -1, __builtin_return_address(0));
@@ -2380,9 +2432,15 @@ EXPORT_SYMBOL(__kmalloc);
 #ifdef CONFIG_NUMA
 void *__kmalloc_node(size_t size, gfp_t flags, int node)
 {
-	struct kmem_cache *s = get_slab(size, flags);
+	struct kmem_cache *s;
+
+	if (unlikely(size > PAGE_SIZE / 2))
+		return (void *)__get_free_pages(flags | __GFP_COMP,
+							get_order(size));
 
-	if (ZERO_OR_NULL_PTR(s))
+	s = get_slab(size, flags);
+
+	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
 	return slab_alloc(s, flags, node, __builtin_return_address(0));
@@ -2395,7 +2453,8 @@ size_t ksize(const void *object)
 	struct page *page;
 	struct kmem_cache *s;
 
-	if (ZERO_OR_NULL_PTR(object))
+	BUG_ON(!object);
+	if (unlikely(object == ZERO_SIZE_PTR))
 		return 0;
 
 	page = get_object_page(object);
@@ -2427,22 +2486,17 @@ EXPORT_SYMBOL(ksize);
 
 void kfree(const void *x)
 {
-	struct kmem_cache *s;
 	struct page *page;
 
-	/*
-	 * This has to be an unsigned comparison. According to Linus
-	 * some gcc version treat a pointer as a signed entity. Then
-	 * this comparison would be true for all "negative" pointers
-	 * (which would cover the whole upper half of the address space).
-	 */
-	if (ZERO_OR_NULL_PTR(x))
+	if (unlikely(ZERO_OR_NULL_PTR(x)))
 		return;
 
 	page = virt_to_head_page(x);
-	s = page->slab;
-
-	slab_free(s, page, (void *)x, __builtin_return_address(0));
+	if (unlikely(!PageSlab(page))) {
+		put_page(page);
+		return;
+	}
+	slab_free(page->slab, page, (void *)x, __builtin_return_address(0));
 }
 EXPORT_SYMBOL(kfree);
 
@@ -2471,7 +2525,7 @@ int kmem_cache_shrink(struct kmem_cache *s)
 		return -ENOMEM;
 
 	flush_all(s);
-	for_each_online_node(node) {
+	for_each_node_state(node, N_NORMAL_MEMORY) {
 		n = get_node(s, node);
 
 		if (!n->nr_partial)
@@ -2500,15 +2554,11 @@ int kmem_cache_shrink(struct kmem_cache *s)
 				slab_unlock(page);
 				discard_slab(s, page);
 			} else {
-				if (n->nr_partial > MAX_PARTIAL)
-					list_move(&page->lru,
-					slabs_by_inuse + page->inuse);
+				list_move(&page->lru,
+				slabs_by_inuse + page->inuse);
 			}
 		}
 
-		if (n->nr_partial <= MAX_PARTIAL)
-			goto out;
-
 		/*
 		 * Rebuild the partial list with the slabs filled up most
 		 * first and the least used slabs at the end.
@@ -2516,7 +2566,6 @@ int kmem_cache_shrink(struct kmem_cache *s)
 		for (i = s->objects - 1; i >= 0; i--)
 			list_splice(slabs_by_inuse + i, n->partial.prev);
 
-	out:
 		spin_unlock_irqrestore(&n->list_lock, flags);
 	}
 
@@ -2561,7 +2610,7 @@ void __init kmem_cache_init(void)
 		caches++;
 	}
 
-	for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
+	for (i = KMALLOC_SHIFT_LOW; i < PAGE_SHIFT; i++) {
 		create_kmalloc_cache(&kmalloc_caches[i],
 			"kmalloc", 1 << i, GFP_KERNEL);
 		caches++;
@@ -2588,7 +2637,7 @@ void __init kmem_cache_init(void)
 	slab_state = UP;
 
 	/* Provide the correct kmalloc names now that the caches are up */
-	for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++)
+	for (i = KMALLOC_SHIFT_LOW; i < PAGE_SHIFT; i++)
 		kmalloc_caches[i]. name =
 			kasprintf(GFP_KERNEL, "kmalloc-%d", 1 << i);
 
@@ -2627,7 +2676,7 @@ static int slab_unmergeable(struct kmem_cache *s)
 }
 
 static struct kmem_cache *find_mergeable(size_t size,
-		size_t align, unsigned long flags,
+		size_t align, unsigned long flags, const char *name,
 		void (*ctor)(void *, struct kmem_cache *, unsigned long))
 {
 	struct kmem_cache *s;
@@ -2641,6 +2690,7 @@ static struct kmem_cache *find_mergeable(size_t size,
 	size = ALIGN(size, sizeof(void *));
 	align = calculate_alignment(flags, align, size);
 	size = ALIGN(size, align);
+	flags = kmem_cache_flags(size, flags, name, NULL);
 
 	list_for_each_entry(s, &slab_caches, list) {
 		if (slab_unmergeable(s))
@@ -2649,8 +2699,7 @@ static struct kmem_cache *find_mergeable(size_t size,
 		if (size > s->size)
 			continue;
 
-		if (((flags | slub_debug) & SLUB_MERGE_SAME) !=
-			(s->flags & SLUB_MERGE_SAME))
+		if ((flags & SLUB_MERGE_SAME) != (s->flags & SLUB_MERGE_SAME))
 				continue;
 		/*
 		 * Check if alignment is compatible.
@@ -2674,7 +2723,7 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 	struct kmem_cache *s;
 
 	down_write(&slub_lock);
-	s = find_mergeable(size, align, flags, ctor);
+	s = find_mergeable(size, align, flags, name, ctor);
 	if (s) {
 		s->refcount++;
 		/*
@@ -2749,9 +2798,14 @@ static struct notifier_block __cpuinitdata slab_notifier =
 
 void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, void *caller)
 {
-	struct kmem_cache *s = get_slab(size, gfpflags);
+	struct kmem_cache *s;
 
-	if (ZERO_OR_NULL_PTR(s))
+	if (unlikely(size > PAGE_SIZE / 2))
+		return (void *)__get_free_pages(gfpflags | __GFP_COMP,
+							get_order(size));
+	s = get_slab(size, gfpflags);
+
+	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
 	return slab_alloc(s, gfpflags, -1, caller);
@@ -2760,9 +2814,14 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, void *caller)
 void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 					int node, void *caller)
 {
-	struct kmem_cache *s = get_slab(size, gfpflags);
+	struct kmem_cache *s;
+
+	if (unlikely(size > PAGE_SIZE / 2))
+		return (void *)__get_free_pages(gfpflags | __GFP_COMP,
+							get_order(size));
+	s = get_slab(size, gfpflags);
 
-	if (ZERO_OR_NULL_PTR(s))
+	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
 	return slab_alloc(s, gfpflags, node, caller);
@@ -2861,7 +2920,7 @@ static long validate_slab_cache(struct kmem_cache *s)
 		return -ENOMEM;
 
 	flush_all(s);
-	for_each_online_node(node) {
+	for_each_node_state(node, N_NORMAL_MEMORY) {
 		struct kmem_cache_node *n = get_node(s, node);
 
 		count += validate_slab_node(s, n, map);
@@ -3081,12 +3140,12 @@ static int list_locations(struct kmem_cache *s, char *buf,
 	/* Push back cpu slabs */
 	flush_all(s);
 
-	for_each_online_node(node) {
+	for_each_node_state(node, N_NORMAL_MEMORY) {
 		struct kmem_cache_node *n = get_node(s, node);
 		unsigned long flags;
 		struct page *page;
 
-		if (!atomic_read(&n->nr_slabs))
+		if (!atomic_long_read(&n->nr_slabs))
 			continue;
 
 		spin_lock_irqsave(&n->list_lock, flags);
@@ -3208,7 +3267,7 @@ static unsigned long slab_objects(struct kmem_cache *s,
 		}
 	}
 
-	for_each_online_node(node) {
+	for_each_node_state(node, N_NORMAL_MEMORY) {
 		struct kmem_cache_node *n = get_node(s, node);
 
 		if (flags & SO_PARTIAL) {
@@ -3221,7 +3280,7 @@ static unsigned long slab_objects(struct kmem_cache *s,
 		}
 
 		if (flags & SO_FULL) {
-			int full_slabs = atomic_read(&n->nr_slabs)
+			int full_slabs = atomic_long_read(&n->nr_slabs)
 					- per_cpu[node]
 					- n->nr_partial;
 
@@ -3236,7 +3295,7 @@ static unsigned long slab_objects(struct kmem_cache *s,
 
 	x = sprintf(buf, "%lu", total);
 #ifdef CONFIG_NUMA
-	for_each_online_node(node)
+	for_each_node_state(node, N_NORMAL_MEMORY)
 		if (nodes[node])
 			x += sprintf(buf + x, " N%d=%lu",
 					node, nodes[node]);
@@ -3257,7 +3316,7 @@ static int any_slab_objects(struct kmem_cache *s)
 	for_each_node(node) {
 		struct kmem_cache_node *n = get_node(s, node);
 
-		if (n->nr_partial || atomic_read(&n->nr_slabs))
+		if (n->nr_partial || atomic_long_read(&n->nr_slabs))
 			return 1;
 	}
 	return 0;
@@ -3780,7 +3839,9 @@ static int __init slab_sysfs_init(void)
 
 	list_for_each_entry(s, &slab_caches, list) {
 		err = sysfs_slab_add(s);
-		BUG_ON(err);
+		if (err)
+			printk(KERN_ERR "SLUB: Unable to add boot slab %s"
+						" to sysfs\n", s->name);
 	}
 
 	while (alias_list) {
@@ -3788,7 +3849,9 @@ static int __init slab_sysfs_init(void)
 
 		alias_list = alias_list->next;
 		err = sysfs_slab_alias(al->s, al->name);
-		BUG_ON(err);
+		if (err)
+			printk(KERN_ERR "SLUB: Unable to add boot slab alias"
+					" %s to sysfs\n", s->name);
 		kfree(al);
 	}